Abstract:
|
Propensity modeling has been extensively used in telecommunication companies to optimize marketing outcomes in cross sale and up sale campaigns, retention tactics, recruiting strategies, etc. By identifying characteristics of customers who are most likely to respond, propensity models make no discrimination between the potential responders that are going to take actions regardless of campaign and those only take action after being treated by campaign. Uplift models, on the other hand, specifically target those that can be influenced by promotional marketing operations. While both modeling methodology are proven useful in many use cases, uplift models are found superior in terms of maximizing return on investment, especially for cross sale and up sale targeting. In this paper we examine the pros and cons of both modeling methodology vs. different scenarios of marketing need, and present empirical suggestions on best practices tactics.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.